irail-mcp
Provides Belgian railway travel information via the iRail API, including station search, live departures/arrivals, route planning, and network disturbances.
README
iRail MCP Server
Disclaimer: This project was vibe coded and is not affiliated with or supported by iRail vzw. Train data may be inaccurate or outdated. Always verify with official sources (belgiantrain.be or the NMBS/SNCB app) before making travel decisions.
A Model Context Protocol (MCP) server that provides Belgian railway travel information via the iRail API.
Features
- Search Stations - Find Belgian railway stations by name
- Live Departures/Arrivals - Real-time departure and arrival boards
- Find Connections - Route planning between stations with transfers
- Train Information - Detailed stops, delays, and platforms for a specific train
- Network Disturbances - Current disruptions and planned maintenance
Installation
Requires Python 3.11+ and uv.
git clone https://github.com/HansF/irail-mcp.git
cd irail-mcp
uv venv && source .venv/bin/activate
uv pip install -e .
Usage with Claude Code
Add to your project's .mcp.json:
{
"mcpServers": {
"irail": {
"command": "uvx",
"args": ["irail-mcp"]
}
}
}
Then ask Claude things like:
- "What trains leave Brussels Central in the next hour?"
- "Find a route from Antwerp to Bruges at 2:30 PM tomorrow"
- "Are there any disruptions on the Belgian rail network?"
- "Show me details for train IC2240"
Tools
search_stations
Search for stations by name.
query(required) - Station name or partial namelang(optional) - Language: en, nl, fr, de, it
get_liveboard
Real-time departures or arrivals from a station.
station(required) - Station namedate(optional) - YYYY-MM-DD, "today", "tomorrow", "+2 days"time(optional) - HH:MM (24h)arrival(optional) - Show arrivals instead of departureslang(optional)
find_connections
Find routes between two stations.
from_station(required) - Departure stationto_station(required) - Destination stationdate,time,lang(optional)arrival_time(optional) - If true, time is desired arrival time
get_train_info
Detailed information about a specific train.
train_id(required) - e.g. "IC1234" or "BE.NMBS.IC1234"date,lang(optional)
get_disturbances
Current network disruptions and planned works.
lang(optional)
Running Tests
uv pip install -e ".[dev]"
python -m pytest tests/ -v
API Compliance
- Rate limited to 3 requests/second per iRail guidelines
- Proper User-Agent header set
- 30-second timeout for slow responses
License
MIT
References
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.